acknowledgments

This book would not be possible without the support of many of our colleagues, collaborators, and countless researchers in the field of artificial intelligence who have chosen to share their explorations of this technology.

We thank our colleagues at Booz Allen Hamilton for their support of this work, including John Larson, Steve Escaravage, Justin Neroda, Catherine Ordun, Jessica Reinhart, and Katrina Jacobs. Andre Nguyen and Matt Keating deserve special recognition for the many conversations on the nature of large language models and ways to think about their safety.

We also want to thank the outstanding staff at Manning Publications, including Frances Lefkowitz, our development editor, and Shreesha Jagadeesh, our technical editor, who both asked the hard questions and shaped and improved the book in so many ways by providing thoughtful feedback. We also thank Andy Waldron, our acquisitions editor; Rebecca Rinehart, our development manager; and Aira Ducic, who led marketing for this book.

We also acknowledge Melissa Ice and Radmila Ercegovac, who orchestrated the reviews throughout the writing process, and all of the anonymous reviewers who provided excellent feedback to make this book what it is today.